Evaluation of Synthetic Datasets for Conversational Recommender Systems. (arXiv:2212.08167v1 [cs.CL])
MM-SHAP: A Performance-agnostic Metric for Measuring Multimodal Contributions in Vision and Language Models & Tasks. (arXiv:2212.08158v1 [cs.CV])
FiDO: Fusion-in-Decoder optimized for stronger performance and faster inference. (arXiv:2212.08153v1 [cs.CL])
Efficient Long Sequence Modeling via State Space Augmented Transformer. (arXiv:2212.08136v1 [cs.CL])
WEKA-Based: Key Features and Classifier for French of Five Countries. (arXiv:2212.08132v1 [cs.CL])
Injecting Domain Knowledge in Language Models for Task-Oriented Dialogue Systems. (arXiv:2212.08120v1 [cs.CL])
Routine Outcome Monitoring in Psychotherapy Treatment using Sentiment-Topic Modelling Approach. (arXiv:2212.08111v1 [cs.CL])
Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text Classification. (arXiv:2212.08105v1 [cs.CL])
The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies. (arXiv:2212.08104v1 [cs.CL])
DFEE: Interactive DataFlow Execution and Evaluation Kit. (arXiv:2212.08099v1 [cs.CL])
Joint processing of linguistic properties in brains and language models. (arXiv:2212.08094v1 [cs.CL])
Constitutional AI: Harmlessness from AI Feedback. (arXiv:2212.08073v1 [cs.CL])
Foresight -- Deep Generative Modelling of Patient Timelines using Electronic Health Records. (arXiv:2212.08072v1 [cs.CL])
Towards mapping the contemporary art world with ArtLM: an art-specific NLP model. (arXiv:2212.07127v2 [cs.CL] UPDATED)
Decomposing a Recurrent Neural Network into Modules for Enabling Reusability and Replacement. (arXiv:2212.05970v2 [cs.SE] UPDATED)
FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification. (arXiv:2212.05506v2 [cs.CL] UPDATED)
Continuous diffusion for categorical data. (arXiv:2211.15089v3 [cs.CL] UPDATED)
Robust Preference Learning for Storytelling via Contrastive Reinforcement Learning. (arXiv:2210.07792v2 [cs.CL] UPDATED)
Towards Generalized and Explainable Long-Range Context Representation for Dialogue Systems. (arXiv:2210.06282v2 [cs.CL] UPDATED)
TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations. (arXiv:2209.07562v2 [cs.CL] UPDATED)
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl